Wear amount estimation system, computation model generation system, and wear amount estimation method

Abstract

To provide an abrasion loss estimation system, a calculation model generation system and an abrasion loss estimation method which can improve the estimation accuracy of an abrasion loss of a tire.SOLUTION: A vehicle information acquisition unit 12 of an abrasion loss estimation system 100 acquires video data detecting a passenger being a loaded object loaded for transportation in a vehicle 6. An image recognition unit 13 recognizes a position of the passenger from the video data acquired by the vehicle information acquisition unit 12. A distribution calculation unit 14 calculates a distribution state of the weight of the passengers in each section sectioned by a stop as a stopping location on the basis of the position of the passenger recognized by the image recognition unit 13. An abrasion loss calculation unit 16 has a calculation model 16a which calculates the abrasion loss of a tire 7 on the basis of input information and calculates the abrasion loss of the tire 7 by inputting the distribution state calculated by the distribution calculation unit 14 to the calculation model 16a.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a wear amount estimation system, a calculation model generation system, and a wear amount estimation method for estimating the amount of wear of a tire mounted on a vehicle. [Background technology]

[0002] In general, tires wear according to driving conditions, distance traveled, etc. Recently, devices that attach sensors to tires to measure tire pressure and temperature and display the measured pressure and temperature have been commercialized.

[0003] Patent Document 1 describes a conventional tire maintenance support system for estimating tire wear. This tire maintenance support system includes a wear progress acquisition unit that acquires the wear progress of the tread and side parts at each mounting position, a wear amount calculation unit that calculates a predicted wear amount, which is the wear amount of the tread and side parts at each mounting position until the vehicle maintenance time based on the acquired wear progress, and a rotation plan selection unit that selects at least one rotation plan from a plurality of rotation plans for switching tires from a predetermined position to another mounting position based on the calculated predicted wear amount. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2018-156125 A Summary of the Invention [Problem to be solved by the invention]

[0005] In the tire maintenance support system described in Patent Document 1, the predicted wear amount of a tire is calculated based on the wear progress of the tread and side at each mounting position. The inventor noticed that there is room for improvement in tire wear amount estimation, since the wear amount of each tire varies depending on the position of the cargo in a vehicle that transports cargo such as passengers, such as a route bus. In addition, the tire wear amount varies depending on factors such as the distance of each section separated by stops such as bus stops, and the acceleration and deceleration of the vehicle at the stops, so the inventor noticed that tire wear amount estimation can be improved by taking these factors into account.

[0006] The present invention has been made in consideration of the above circumstances, and an object of the present invention is to provide a wear amount estimation system, a calculation model generation system, and a wear amount estimation method that can improve the accuracy of estimating the amount of wear of a tire. [Means for solving the problem]

[0007] A wear amount estimation system according to one embodiment of the present invention comprises a vehicle information acquisition unit that acquires data detecting cargo loaded inside a vehicle for transportation, a recognition unit that recognizes the position of the cargo from the data acquired by the vehicle information acquisition unit, a distribution calculation unit that calculates the distribution of cargo weight in each section separated by stops based on the position of the cargo recognized by the recognition unit, and a wear amount calculation unit that has a computational model that calculates the amount of tire wear based on input information, and inputs the distribution calculated by the distribution calculation unit into the computational model to calculate the amount of wear of the tire.

[0008] Another aspect of the present invention is a computation model generation system. The computation model generation system includes a vehicle information acquisition unit that acquires data of detected cargo loaded inside a vehicle for transportation, a recognition unit that recognizes the position of the cargo from the data acquired by the vehicle information acquisition unit, a distribution calculation unit that calculates a distribution state of weight of the cargo in each section separated by stops based on the position of the cargo recognized by the recognition unit, a wear amount calculation unit that has a computation model that calculates tire wear amount based on input information and inputs the distribution state calculated by the distribution calculation unit to the computation model to calculate the wear amount of the tire, and a learning processing unit that learns the computation model by comparing the wear amount measured on the tire with the wear amount calculated by the wear amount calculation unit.

[0009] Another aspect of the present invention is a wear amount estimation method, which includes a vehicle information acquisition step of acquiring data detecting a load loaded inside a vehicle for transportation, a recognition step of recognizing a position of the load from the data acquired by the vehicle information acquisition step, a distribution calculation step of calculating a distribution state of the load in each section separated by stops based on the position of the load recognized by the recognition step, and a wear amount calculation step of having a calculation model for calculating tire wear amount based on input information, inputting the distribution state calculated by the distribution calculation step into the calculation model to calculate the tire wear amount. Effect of the Invention

[0010] According to the present invention, it is possible to improve the accuracy of estimating the amount of wear of a tire. [Brief description of the drawings]

[0011] [Figure 1] 1 is a block diagram showing a functional configuration of a wear amount estimation system according to an embodiment; [Diagram 2] FIG. 2 is a block diagram showing a functional configuration of the vehicle-mounted measuring device. [Diagram 3] FIG. 2 is a plan view of the interior of the vehicle as viewed from above. [Figure 4] 4 is a table showing an example of tire severity information generated by a tire severity generating unit. [Diagram 5] FIG. 1 is a schematic diagram showing an example of a route on which a vehicle travels. [Figure 6] 10 is a schematic diagram for explaining wear amount estimation and learning of a computation model. FIG. [Figure 7] FIG. 2 is a block diagram showing a functional configuration of the computation model generation system. [Figure 8] 1 is a flowchart showing a procedure for generating a computation model by the computation model generation system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] The present invention will be described below based on preferred embodiments with reference to Figures 1 to 8. The same or equivalent components and members shown in each drawing are given the same reference numerals, and duplicated descriptions are omitted as appropriate. The dimensions of the members in each drawing are enlarged or reduced as appropriate for ease of understanding. Some of the members that are not important for explaining the embodiments are omitted in each drawing.

[0013] (Embodiment) 1 is a block diagram showing a functional configuration of a wear amount estimation system 100 according to an embodiment. The wear amount estimation system 100 includes an on-vehicle measurement device 70 mounted on a vehicle 6, a weather information server device 80, and a wear amount estimation device 10 that estimates the amount of wear of each tire 7 mounted on the vehicle 6.

[0014] The wear amount estimation system 100 estimates the wear amount of each tire 7 mounted on a vehicle 6 that travels along a set route to transport passengers and other cargo. The vehicle 6 is, for example, a route bus, which includes a starting stop and a terminal stop as stops, and transports passengers by boarding and disembarking at each stop between the starting stop and the terminal stop. The starting stop and the terminal stop may be the same or different. The vehicle 6 is also a transport truck with a preset route, which loads and unloads cargo such as luggage at stops including a starting point, an arrival point, and a stop on the way, and transports the cargo. The following description will be given using a route bus as an example of the vehicle 6, but the same applies when the vehicle 6 is a transport truck, and the stops of the route bus are replaced with stops of the transport truck, and the passengers loaded onto the vehicle 6 are replaced with luggage loaded onto the transport truck. In the present invention, the stops of the vehicle 6 are the departure point, arrival point, and loading and unloading stops in the case of a transport truck, and each bus stop in the case of a route bus.

[0015] The route is formed by connecting sections separated by bus stops. The wear amount estimation system 100 estimates the wear amount of each tire 7 using information such as the known travel distance, number of turns, turning direction, and elevation difference in each section, as well as information such as the acceleration of the vehicle 6 measured during travel and the distribution of passenger weight. The route is not limited to a predetermined one, and when a service schedule including a route from a departure point to a destination is created, information such as the travel distance and number of turns of the route may be obtained from an external computer-assisted map routing service.

[0016] The wear amount estimation device 10 acquires vehicle measurement information such as the speed, acceleration, and position information of the vehicle 6 from an on-board measurement device 70 mounted on the vehicle 6 via a communication network 9 such as the Internet, as well as tire measurement information measured on the tires 7. The wear amount estimation device 10 also acquires weather information from a weather information server device 80. The wear amount estimation device 10 estimates the amount of wear of each tire 7 by performing calculations using a learning-type calculation model based on the acquired information.

[0017] 2 is a block diagram showing the functional configuration of the on-vehicle measurement device 70. The on-vehicle measurement device 70 includes a vehicle measurement unit 71, a tire measurement unit 72, an in-vehicle image capture unit 73, an information acquisition unit 74, and a communication unit 75. Each unit in the on-vehicle measurement device 70 can be realized in terms of hardware by electronic elements and mechanical parts such as a computer CPU, and in terms of software by a computer program, but here, functional blocks realized by the cooperation of these are depicted. Therefore, it will be understood by those skilled in the art that these functional blocks can be realized in various forms by combining hardware and software.

[0018] The vehicle measurement unit 71 has a speedometer 71a and an acceleration sensor 71b mounted on the vehicle 6. The speedometer 71a measures the speed of the vehicle. The acceleration sensor 71b measures the acceleration in three axial directions of the vehicle 6. The vehicle measurement unit 71 may have a device that measures position information of the vehicle 6.

[0019] The tire measurement unit 72 has a temperature sensor 72a and a pressure sensor 72b. The temperature sensor 72a and the pressure sensor 72b are disposed on an air valve or the like of a tire 7 mounted on the vehicle 6, or are firmly wrapped around and fixed to a wheel with a belt or the like, and measure the temperature and air pressure of the tire 7. The temperature sensor 72a may be disposed on an inner liner or the like of the tire 7. Furthermore, the tire measurement unit 72 may include an acceleration sensor in its configuration to obtain more detailed tire information.

[0020] The interior image capturing unit 73 is a camera device having a detector such as a CCD, captures images of the interior of the vehicle, and generates image data of the interior of the vehicle. The interior image capturing unit 73 may add information such as the time of capture and arrival / departure / stop times at bus stops to the image data captured of the interior of the vehicle.

[0021] The information acquisition unit 74 acquires vehicle measurement information (speed, acceleration, etc.) measured by the vehicle measurement unit 71, tire measurement information (tire temperature, air pressure, etc.) measured by the tire measurement unit 72, and video data captured by the in-vehicle imaging unit 73. The information acquisition unit 74 associates measured time information or acquired time information with each piece of measurement data included in the vehicle measurement information and tire measurement information.

[0022] The information acquisition unit 74 transmits the vehicle measurement information and the tire measurement information together with time information associated with each measurement data from the communication unit 75 to the wear amount estimation device 10. The information acquisition unit 74 also transmits video data captured by the in-vehicle imaging unit 73 from the communication unit 75 to the wear amount estimation device 10.

[0023] When the vehicle 6 is equipped with a device such as a digital tachometer, the information acquisition unit 74 may acquire information such as the speed and acceleration of the vehicle 6 collected by that device. The communication unit 75 is connected to the communication network 9 by wireless communication such as WiFi (registered trademark), and transmits the video data, vehicle measurement information, and tire measurement information (including time information) acquired by the information acquisition unit 74 to the wear amount estimation device 10 via the communication network 9.

[0024] 1, the weather information server device 80 provides weather information for various locations. The weather information provided by the weather information server device 80 includes the amount of precipitation, the amount of snowfall, the temperature, and the hours of sunshine for various locations. The wear amount estimation device 10 obtains from the weather information server device 80 the weather information for the location where the vehicle 6 is traveling.

[0025] The wear amount estimation device 10 includes a communication unit 11, a vehicle information acquisition unit 12, an image recognition unit 13, a distribution calculation unit 14, a tire severity generation unit 15, a wear amount calculation unit 16, and a memory unit 17. Each unit in the wear amount estimation device 10 can be realized in terms of hardware by electronic elements and mechanical parts such as a computer CPU, and in terms of software by a computer program, but here, functional blocks realized by the cooperation of these are depicted. Therefore, it will be understood by those skilled in the art that these functional blocks can be realized in various forms by combining hardware and software.

[0026] The communication unit 11 is connected to the communication network 9 by wireless or wired communication, and communicates with a communication unit 75 of the on-vehicle measuring device 70. The communication unit 11 also communicates with a weather information server device 80 via the communication network 9.

[0027] The vehicle information acquisition unit 12 acquires vehicle measurement information, tire measurement information, and video data captured inside the vehicle, transmitted from an on-board measurement device 70 mounted on the vehicle 6. The vehicle information acquisition unit 12 outputs the acquired video data to the image recognition unit 13. The vehicle information acquisition unit 12 outputs the acquired tire measurement information (tire temperature, air pressure, etc.) to the wear amount calculation unit 16. The vehicle information acquisition unit 12 outputs information on the vehicle measurement information (speed and acceleration) to the tire severity generation unit 15.

[0028] The vehicle information acquisition unit 12 acquires data used to estimate the wear amount of the tires 7 from among the vehicle specification data 17a, the tire specification data 17b, and the tire position data 17c from the storage unit 17, and outputs the data to the wear amount calculation unit 16. The vehicle information acquisition unit 12 also acquires route data 17d from the storage unit 17, and outputs the data to the tire severity generation unit 15. The route data 17d may be acquired from an external computer-assisted map routing service based on each stop including the departure point, intermediate points, and arrival point.

[0029] The memory unit 17 is a storage device composed of, for example, an SSD (Solid State Drive), a hard disk, a CD-ROM, a DVD, etc., and stores data provided in advance regarding the specifications of various vehicles and tires 7, as well as route data regarding the routes on which the vehicle 6 travels.

[0030] The vehicle specification data 17a includes information on vehicle performance such as the manufacturer, vehicle name, vehicle model, vehicle weight, drive train, overall length, vehicle width, vehicle height, and maximum load capacity. The tire specification data 17b includes information on tire 7 performance such as the manufacturer, product name, tire size, tire width, aspect ratio, wear resistance, tire strength, static stiffness, dynamic stiffness, tire outer diameter, load index, and manufacturing date. The tire position data 17c includes information on the position of the tire to be predicted to wear on the vehicle and the axle on which it is mounted. The route data 17d includes data on the distance of each section between stops, information on turns, altitude change, number of altitude changes, and altitude change amount.

[0031] The image recognition unit 13 performs image recognition of passengers and their positions in the vehicle from the video data captured inside the vehicle. When there are multiple passengers, the image recognition unit 13 recognizes the position of each passenger. The image recognition unit 13 outputs the image-recognized position of each passenger to the distribution calculation unit 14. The image recognition unit 13 can use various known image recognition methods for recognizing people from captured video data in the technical field of image recognition, and can use an image recognition method using a learning model, for example. The image recognition unit 13 corresponds to the recognition unit in the present invention. The video data used by the image recognition unit 13 corresponds to data used by the recognition unit to recognize the position of a load. The configuration for detecting the position of a passenger is not limited to the configuration using the image recognition unit 13, and may be a configuration including a sensor device that performs object detection using ultrasonic waves or radio waves (millimeter waves), for example, by echolocation technology.

[0032] The distribution calculation unit 14 calculates the distribution of passenger weight based on the position of each passenger inside the vehicle recognized by the image recognition unit 13, and outputs the calculated weight to the wear amount calculation unit 16. Fig. 3 is a plan view of the interior of the vehicle 6 viewed from above. A driver's seat 61 is provided on the right side of the very front of the vehicle 6, and seats 62 are provided from behind the driver's seat 61 to the very rear of the vehicle 6. Tires 7 are mounted on the left and right sides of the front and rear of the vehicle 6.

[0033] In the example shown in Fig. 3, the interior of the vehicle is divided into four areas: area A1 including the right front wheel, area A2 including the left front wheel, area A3 including the right rear wheel, and area A4 including the left rear wheel. The distribution calculation unit 14 determines which of areas A1 to A4 each passenger belongs to based on the position of each passenger, and calculates the number of passengers present in each area. Note that the driver is included in the passengers in area A1 when calculating the number of passengers.

[0034] The distribution calculation unit 14 calculates the distribution of passenger weights assuming that the passenger weights are the same. For example, when it is determined that there are four passengers in the area A1, three passengers in the area A2, three passengers in the area A3, and two passengers in the area A4, the distribution calculation unit 14 calculates the distribution of passenger weights as 3 in the area A1, 3 in the area A2, 3 in the area A3, and 2 in the area A4. When the image recognition unit 13 is capable of image recognition of adults and children, the distribution calculation unit 14 may set the weight of an adult to 1 and the weight of a child to 0.5, for example. Furthermore, the distribution calculation unit 14 may calculate that the distribution in the area A1 is 240 kg when the passenger weight is, for example, 60 kg and there are four passengers in the area A1. Furthermore, a device capable of measuring the weight of a passenger may be installed at the entrance of the vehicle to measure the actual weight of the passengers, and a more detailed weight distribution may be calculated.

[0035] The tire severity generation unit 15 generates severity information on tire wear (hereinafter referred to as tire severity information) based on information such as the distance of each section on the route on which the vehicle 6 travels, and outputs it to the wear amount calculation unit 16.

[0036] FIG. 4 is a chart showing an example of tire severity information generated by the tire severity generation unit 15. The tire severity information is classified into four categories: driving-related, turning-related, starting / stopping-related, and elevation difference-related. For driving-related information, the tire severity generation unit 15 generates the distance of each section separated by stops and the speed of the vehicle as tire severity information. The longer the distance of each section and the higher the vehicle speed in each section, the greater the amount of wear of the tires 7. The remarks column in FIG. 4 shows the source of data used as tire severity information. The distance of each section is known depending on the route and is obtained from the route data 17d. The speed of the vehicle is measured by the speedometer 71a and obtained from the on-board measuring device 70.

[0037] Fig. 5 is a schematic diagram showing an example of a route on which the vehicle 6 travels. In the example of the route shown in Fig. 5, the vehicle 6 starts and ends at bus stop ST1, and travels in a loop via bus stops ST2 and ST3. For example, turning points P1 to P3 exist between bus stops ST1 and ST2. The turning points P1 to P9 on which the vehicle 6 travels are known according to the route, and are included in the route data 17d.

[0038] In relation to turning, the tire severity generating unit 15 generates the turning radius, turning direction, turning speed, and lateral acceleration at turning points in each section separated by bus stops as tire severity information. The smaller the turning radius and the greater the turning speed and lateral acceleration at a turning point, the greater the wear of the tires 7. Also, the wear of the tires 7 on the right or left side of the vehicle 6 increases depending on the turning direction. The turning speed and lateral acceleration at each turning point are measured by the speedometer 71a and acceleration sensor 71b, and are acquired from the on-board measuring device 70.

[0039] In relation to departure and stopping, the tire severity generating unit 15 generates the speed and acceleration when the vehicle stops at each stop, and the speed and acceleration when the vehicle starts as tire severity information. The larger the speed and lateral acceleration when the vehicle stops and starts, the greater the amount of wear on the tires 7. The speed and acceleration when the vehicle stops at each stop, and the speed and acceleration when the vehicle starts are measured by the speedometer 71a and the acceleration sensor 71b, and are acquired from the on-board measuring device 70.

[0040] In relation to elevation difference, the tire severity generating unit 15 generates the amount of altitude change, the number of altitude changes, and the direction of altitude change as tire severity information for each section. The amount of altitude change is, for example, a total amount of change obtained by accumulating the absolute values ​​of the altitude difference due to ascent and descent of the road in each section. The number of altitude changes is, for example, a total number of changes obtained by accumulating the number of ascents and descents of the road in each section. The direction of altitude change indicates, for example, whether each section is generally upward or downward.

[0041] The greater the amount of change in altitude and the number of altitude changes in each section, the greater the amount of wear on the tires 7. Also, depending on the direction of the altitude change, the amount of wear on the front or rear tires 7 increases. The amount of change in altitude, the number of altitude changes, and the direction of the altitude change in each section are known and are included in the route data 17d.

[0042] The wear amount calculation unit 16 has a calculation model 16a and estimates the wear amount of the tire 7. The calculation model 16a is a learning model that calculates the wear amount of the tire 7 based on input information. Fig. 6 is a schematic diagram for explaining the wear amount estimation and learning of the calculation model 16a. The input data to the calculation model 16a is roughly classified into each system of vehicle measurement information, tire measurement information, passenger weight distribution status, tire severity information, and other information.

[0043] The input data related to the vehicle measurement information includes the speed and acceleration of the vehicle 6. In the tire severity generation unit 15, the speed and acceleration at the time of starting and stopping are used as tire severity information, but the speed and acceleration during traveling within the section may be used as input data to the calculation model 16a. The input data related to the tire measurement information includes the temperature and air pressure of the tire 7.

[0044] The input data relating to tire severity information is tire severity information calculated by the tire severity generating unit 15. The tire severity information is data relating to running, turning, starting and stopping, and elevation difference, as described above.

[0045] The input data based on other information includes road surface conditions, temperature, precipitation, etc. estimated based on meteorological information, the maximum load capacity of the vehicle included in the vehicle specification data 17a, and the wear resistance performance of the tire 7 included in the tire specification data 17b. The wear resistance performance of the tire 7 is measured using, for example, a tire wear index value obtained by indexing the wear resistance performance of various tread blends based on a Lambourn wear test with a standard blend being set at 100. The input data based on other information is information related to the position and axle of the tire 7 included in the tire position data 17c.

[0046] The computation model 16a uses a learning model such as a neural network. The computation model 16a is constructed using a method such as a deep neural network (DNN) or a decision tree. The computation model 16a may be a multiple linear regression model for input information, which is generated by learning.

[0047] 7 is a block diagram showing the functional configuration of the computation model generation system 110. In addition to the configuration of the wear amount estimation system 100, the computation model generation system 110 includes a tire wear amount measuring device 60 and a computation model generation device 20 having a learning processing unit 21.

[0048] The tire wear measuring device 60 directly measures the depth of the grooves provided in the tread of the tire 7 to obtain the wear of the tire 7. An operator may measure the depth of each groove using a measuring tool, a camera, visual inspection, or the like, and the tire wear measuring device 60 may store the measurement data input by the operator. Alternatively, the tire wear measuring device 60 may be a dedicated device that measures the groove depth by a mechanical or optical method and stores the wear amount.

[0049] Specifically, for example, if a tire has four grooves, the tire wear measuring device 60 measures at four locations in the width direction, and further measures at three locations in the circumferential direction of the same groove, for example, at 120° intervals. As a result, uneven wear data in the width direction or circumferential direction of the tire is also stored in the tire wear measuring device 60. Note that the tire wear measuring device 60 may indirectly measure the groove depth by calculation from the travel distance and the tire rotation speed / speed information, since the diameter of the tire changes due to wear. In addition, a device that directly measures the groove depth may be used in combination with a device that predicts the depth by calculation from the travel distance and the tire rotation speed / speed.

[0050] The computation model generating device 20 has a learning processing unit 21 in addition to each component of the wear amount estimation device 10. The parts of the computation model generating device 20 corresponding to each component of the wear amount estimation device 10 have the same functions as those of the wear amount estimation device 10, but the computation model 16a is either before learning or is currently being learned.

[0051] The learning processing unit 21 acquires the wear amount of the tire 7 from the tire wear amount measuring device 60 via the communication unit 11. With reference to Fig. 6, in the learning process of the calculation model 16a, the wear amount of the tire 7 is estimated as output data by the calculation model 16a based on the input information, and is compared with teacher data. The wear amount of the tire 7 measured by the tire wear amount measuring device 60 is used as the teacher data.

[0052] The learning processing unit 21 performs learning by comparing the wear amount of the tire 7 estimated by the computation model 16a with the teacher data, setting various coefficients in the computation process such as weighting to the computation model 16a, and repeatedly updating the model. The wear amount estimation system 100 estimates the wear amount of the tire 7 using the computation model 16a that has been trained by the computation model generation system 110. The learning processing unit 21 can use a known learning method such as gradient boosting. Also, known verification methods such as random data sampling and cross verification can be used to verify the computation model 16a.

[0053] Next, the operation of the wear amount estimation system 100 and the computation model generation system 110 will be described. FIG. 8 is a flowchart showing the procedure of computation model generation by the computation model generation system 110. The vehicle information acquisition unit 12 of the computation model generation device 20 starts acquiring vehicle measurement information, tire measurement information, and video data (S1). In addition, in step S1, the vehicle information acquisition unit 12 reads out necessary information such as vehicle specifications, tire specifications, tire positions, maximum vehicle load, tire wear resistance performance, and route data as other information from the storage unit 17. The image recognition unit 13 performs image recognition of passengers and their positions based on the video data (S2). The distribution calculation unit 14 calculates the distribution of weights by passengers based on the image-recognized positions of each passenger (S3).

[0054] The tire severity generating unit 15 generates tire severity information based on each of the related data of driving, turning, starting and stopping, and elevation difference (S3). As described above, the tire severity information is generated using the information on the speed and acceleration of the vehicle 6 measured by the on-board measuring device 70 and the data included in the route data 17d.

[0055] The wear amount calculation unit 16 acquires input data from the vehicle information acquisition unit 12 and the tire severity generation unit 15, and calculates and estimates the wear amount of the tire 7 using the calculation model 16a (S5). When the road surface condition or the like is used as input data for the calculation model 16a, a processing unit (not shown) for estimating the road surface condition is provided, and the estimated road surface condition is input from the processing unit to the wear amount calculation unit 16.

[0056] The learning processing unit 21 compares the amount of wear of the tire 7 calculated by the computation model 16a with the amount of wear of the tire 7 measured by the tire wear amount measuring device 60 as teacher data (S6). The learning processing unit 21 updates the computation model 16a based on the comparison result in step S6 (S7) and ends the process. The computation model generating device 20 repeats these processes to update the computation model 16a, thereby improving the accuracy of estimating the amount of tire wear.

[0057] The wear amount estimation system 100 estimates the wear amount of the tire 7 by using the trained computation model 16a generated by the computation model generating device 20. The wear amount estimation system 100 estimates the wear amount of the tire 7 by executing the processes from step S1 to step S5 in the flowchart shown in FIG.

[0058] The wear amount estimation system 100 calculates the distribution of passenger weights based on image data captured inside the vehicle and uses the calculated distribution as input data for the computation model 16a, thereby improving the accuracy of the wear amount estimation of the tire 7. Similarly, the computation model generation system 110 calculates the distribution of passenger weights based on image data captured inside the vehicle and uses the calculated distribution as input data for the computation model 16a, thereby generating the computation model 16a that accurately estimates the wear amount of the tire 7.

[0059] The wear amount estimation system 100 can also construct a computation model 16a that outputs the amount of uneven wear of the tire 7 and estimate the amount of uneven wear. In this case, the wear amount estimation system 100 estimates the uneven wear of the tire 7 caused by the distribution of weight of passengers, etc. The computation model generation system 110 can generate a computation model 16a that estimates the amount of uneven wear by having the computation model 16a learn the amount of wear measured in each groove of the tire as teacher data for uneven wear.

[0060] The tire severity generating unit 15 generates the distance of each section divided by bus stops as the severity information for tire wear. The wear amount estimation system 100 can further improve the accuracy of estimating the amount of wear of the tires 7 by using the distance of each section and the weight distribution state of passengers as input data for the calculation model 16a.

[0061] As described above, the wear amount estimation system 100 uses each piece of data that contributes to the wear amount of the tires 7 in relation to driving, turning, starting and stopping, and elevation difference, thereby enabling the wear amount estimation system 100 to further improve the accuracy of estimating the wear amount of the tires 7. The wear amount estimation system 100 uses the distance in each section and the vehicle speed in relation to driving, and the turning radius, turning direction, turning speed, lateral acceleration, and the like in relation to turning, as tire severity information, thereby enabling the wear amount estimation system 100 to further improve the accuracy of estimating the wear amount of the tires 7.

[0062] In relation to starting and stopping, the wear amount estimation system 100 can further improve the accuracy of estimating the amount of wear of the tires 7 by using the speed and acceleration when the vehicle is stopped and the speed and acceleration when the vehicle is starting as tire severity information. In relation to elevation difference, the wear amount estimation system 100 can further improve the accuracy of estimating the amount of wear of the tires 7 by using the amount of altitude change in each section, the number of altitude changes, the direction of altitude change, and the like as tire severity information.

[0063] The computation model generation system 110 can generate a computation model 16a that accurately estimates the amount of tire wear by using each piece of data that contributes to the amount of tire wear in relation to driving, turning, starting and stopping, and elevation difference as input data for the computation model 16a.

[0064] When the wear amount estimation system 100 is equipped with a GPS sensor that acquires position information by a GPS (Global Positioning Satellite), the wear amount estimation system 100 may be configured to use the position information acquired by the GPS sensor. That is, the wear amount estimation system 100 may calculate information such as a turning radius, a turning direction, a turning speed, a speed at the time of starting and stopping, an amount of change in altitude, a number of changes in altitude, and a direction of change in altitude, instead of input data related to vehicle measurement information, based on the position information acquired by the GPS sensor, and use the information as input data to the calculation model 16a. Similarly, the calculation model generation system 110 may calculate information such as a turning radius, a turning direction, a turning speed, a speed at the time of starting and stopping, an amount of change in altitude, a number of changes in altitude, and a direction of change in altitude, instead of input data related to vehicle measurement information, based on the position information acquired by the GPS sensor, and use the information as input data to the calculation model 16a.

[0065] Next, features of the wear amount estimation system 100 and the computation model generation system 110 according to each embodiment will be described. The wear amount estimation system 100 includes a vehicle information acquisition unit 12, an image recognition unit 13 as a recognition unit, a distribution calculation unit 14, and a wear amount calculation unit 16. The vehicle information acquisition unit 12 acquires video data detecting passengers, which are cargo loaded in the vehicle 6 for transportation. The distribution calculation unit 14 calculates the distribution of passenger weights in each section separated by bus stops as stops, based on the positions of the passengers recognized by the image recognition unit 13. The wear amount calculation unit 16 has a calculation model 16a that calculates the wear amount of the tire 7 based on input information, and inputs the distribution calculated by the distribution calculation unit 14 to the calculation model 16a to calculate the wear amount of the tire 7. As a result, the wear amount estimation system 100 can improve the accuracy of the wear amount estimation of the tire 7 by using the distribution of passenger weights in the vehicle as input data for the calculation model 16a.

[0066] The wear amount estimation system 100 further includes a tire severity generation unit 15 that generates the distance of the section divided by bus stops as severity information for tire wear. The wear amount calculation unit 16 inputs the severity information generated by the tire severity generation unit 15 to a calculation model 16a to calculate the wear amount of the tires 7. In this way, the wear amount estimation system 100 can further improve the accuracy of estimating the wear amount of the tires 7 by using the distance of each section and the distribution state of weights by passengers as input data for the calculation model 16a.

[0067] In addition, the tire severity generation unit 15 generates information on the turning of the vehicle 6 in the section separated by bus stops as the severity information. This enables the wear amount estimation system 100 to further improve the accuracy of the wear amount estimation of the tire 7 by using the information on the turning of the vehicle 6 as input data for the calculation model 16a.

[0068] In addition, the tire severity generating unit 15 generates the acceleration when the bus stops at a bus stop and when the bus starts as the severity information. This allows the wear amount estimation system 100 to use the acceleration when the bus stops and when the bus starts as input data for the calculation model 16a, thereby further improving the accuracy of the wear amount estimation of the tire 7.

[0069] In addition, the tire severity generating unit 15 generates information on the elevation difference in the section divided by the bus stops as the severity information. This allows the wear amount estimation system 100 to use the information on the elevation difference as input data for the calculation model 16a, thereby further improving the accuracy of the wear amount estimation of the tire 7.

[0070] The computation model generation system 110 includes a vehicle information acquisition unit 12, an image recognition unit 13 as a recognition unit, a distribution calculation unit 14, a wear amount calculation unit 16, and a learning processing unit 21. The vehicle information acquisition unit 12 acquires video data that detects passengers, which are cargo loaded in the vehicle 6 for transportation. The distribution calculation unit 14 calculates the distribution of passenger weights in each section separated by bus stops as stops, based on the positions of the passengers recognized by the image recognition unit 13. The wear amount calculation unit 16 has a computation model 16a that calculates the wear amount of the tire 7 based on input information, and inputs the distribution calculated by the distribution calculation unit 14 to the computation model 16a to calculate the wear amount of the tire 7. The learning processing unit 21 makes the computation model 16a learn by comparing the wear amount measured on the tire 7 with the wear amount calculated by the wear amount calculation unit 16. As a result, the computation model generation system 110 can generate the computation model 16a that accurately estimates the wear amount of the tire 7.

[0071] The wear amount estimation method includes a vehicle information acquisition step, an image recognition step as a recognition step, a distribution calculation step, and a wear amount calculation step. The vehicle information acquisition step acquires video data detecting passengers, which are cargo loaded in the vehicle 6 for transportation. The image recognition step recognizes the positions of the passengers from the video data acquired by the vehicle information acquisition step. The distribution calculation step calculates the distribution of passenger weights in each section separated by bus stops as stops, based on the positions of the passengers recognized by the image recognition step. The wear amount calculation step has a calculation model 16a that calculates the wear amount of the tire 7 based on input information, and inputs the distribution calculated by the distribution calculation step into the calculation model 16a to calculate the wear amount of the tire 7. According to this method, the distribution of passenger weights in the vehicle can be used as input data for the calculation model 16a, thereby improving the accuracy of the wear amount estimation.

[0072] The above description is based on the embodiments of the present invention. These embodiments are merely examples, and it will be understood by those skilled in the art that various modifications and changes are possible within the scope of the claims of the present invention, and that such modifications and changes are also within the scope of the claims of the present invention. Therefore, the descriptions and drawings in this specification should be treated as illustrative rather than restrictive. [Explanation of symbols]

[0073] 6 vehicle, 7 tire, 12 vehicle information acquisition unit, 13 image recognition unit (recognition unit), 14 distribution calculation unit, 15 tire severity generation unit, 16 wear amount calculation unit, 16a computation model, 21 learning processing unit, 100 wear amount estimation system, 110 computational model generation system.

Claims

1. a vehicle information acquisition unit that acquires data on detected cargo loaded for transportation inside the vehicle; a recognition unit that recognizes a position of a load from the data acquired by the vehicle information acquisition unit; a distribution calculation unit that calculates a distribution state of weights of the cargo in each section divided by stops based on the position of the cargo recognized by the recognition unit; a tire severity generating unit that generates the distance of the section as severity information for tire wear; a wear amount calculation unit having a calculation model for calculating a wear amount of a tire based on input information, the wear amount calculation unit inputting the distribution state calculated by the distribution calculation unit and the severity information generated by the tire severity generation unit to the calculation model to calculate the wear amount of the tire; A wear amount estimation system comprising:

2. 2. The wear amount estimation system according to claim 1, wherein the tire severity generation unit generates information regarding turning of the vehicle in the section as the severity information.

3. 2. The wear amount estimation system according to claim 1, wherein the tire severity generating unit generates, as the severity information, acceleration when the vehicle is stopped at a stop and when the vehicle is starting.

4. 2. The wear amount estimation system according to claim 1, wherein the tire severity generation unit generates information regarding an elevation difference in the section as the severity information.

5. a vehicle information acquisition unit that acquires data on detected cargo loaded for transportation inside the vehicle; a recognition unit that recognizes a position of a load from the data acquired by the vehicle information acquisition unit; a distribution calculation unit that calculates a distribution state of weights of the cargo in each section divided by stops based on the position of the cargo recognized by the recognition unit; a tire severity generating unit that generates the distance of the section as severity information for tire wear; a wear amount calculation unit having a calculation model for calculating a wear amount of a tire based on input information, the wear amount calculation unit inputting the distribution state calculated by the distribution calculation unit and the severity information generated by the tire severity generation unit to the calculation model to calculate the wear amount of the tire; a learning processing unit that learns the calculation model by comparing the amount of wear measured on the tire with the amount of wear calculated by the wear amount calculation unit; A computational model generation system comprising:

6. A vehicle information acquisition step in which the wear amount estimation system acquires data on detected cargo loaded for transportation inside the vehicle; a recognition step in which the wear amount estimation system recognizes a position of a load from the data acquired by the vehicle information acquisition step; a distribution calculation step in which the wear amount estimation system calculates a distribution state of weight of the cargo in each section divided by stops based on the position of the cargo recognized in the recognition step; a tire severity generation step in which the wear amount estimation system generates the distance of the section as severity information for tire wear; a wear amount calculation step in which the wear amount estimation system inputs the distribution state calculated in the distribution calculation step and the severity information generated in the tire severity generation step into a calculation model that calculates the wear amount of the tire based on input information, and calculates the wear amount of the tire; A wear amount estimating method comprising:

Images